-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 75.2k • 184 -
microsoft/xclip-base-patch32
Video Classification • 0.2B • Updated • 145k • 109 -
MCG-NJU/videomae-base
Video Classification • 94.2M • Updated • 71.4k • 50 -
OpenGVLab/VideoMAEv2-Base
Video Classification • 86.2M • Updated • 15.8k • 12
Alban NYANTUDRE
anyantudre
AI & ML interests
ML Engineer 👨🏾💻| Deep Learning (Vision, Language, Speech)
Recent Activity
liked a Space 9 days ago
openai/whisper updated a collection 21 days ago
Mooré - Burkina Faso 🇧🇫 liked a model 21 days ago
YatharthS/LavaSROrganizations
Let’s help Mooré language shine in the world of AI 💛🇧🇫
My favorite Spaces.
-
MinerU OCR
📚555A data extraction tool to convert PDF to Markdown and JSON
-
DeepSeek OCR 2 Demo
🚀448Try out DeepSeek-OCR-2 on your PDFs or images
-
granite-docling-258M demo
📝269Extract and convert document content from images
-
Multimodal RAG with Granite Vision
🚀38RAG example using Granite [vision, embedding, instruct]
My favorite small LLMs and VLMs.
-
OpenGVLab/InternVL3-1B
Image-Text-to-Text • 0.9B • Updated • 101k • 79 -
vikhyatk/moondream2
Image-Text-to-Text • 2B • Updated • 5.16M • 1.39k -
microsoft/Florence-2-base
Image-Text-to-Text • 0.2B • Updated • 738k • 354 -
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Image-Text-to-Text • 0.3B • Updated • 154k • 98
-
facebook/vjepa2-vitl-fpc64-256
Video Classification • 0.3B • Updated • 75.2k • 184 -
microsoft/xclip-base-patch32
Video Classification • 0.2B • Updated • 145k • 109 -
MCG-NJU/videomae-base
Video Classification • 94.2M • Updated • 71.4k • 50 -
OpenGVLab/VideoMAEv2-Base
Video Classification • 86.2M • Updated • 15.8k • 12
-
MinerU OCR
📚555A data extraction tool to convert PDF to Markdown and JSON
-
DeepSeek OCR 2 Demo
🚀448Try out DeepSeek-OCR-2 on your PDFs or images
-
granite-docling-258M demo
📝269Extract and convert document content from images
-
Multimodal RAG with Granite Vision
🚀38RAG example using Granite [vision, embedding, instruct]
Let’s help Mooré language shine in the world of AI 💛🇧🇫
My favorite small LLMs and VLMs.
-
OpenGVLab/InternVL3-1B
Image-Text-to-Text • 0.9B • Updated • 101k • 79 -
vikhyatk/moondream2
Image-Text-to-Text • 2B • Updated • 5.16M • 1.39k -
microsoft/Florence-2-base
Image-Text-to-Text • 0.2B • Updated • 738k • 354 -
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Image-Text-to-Text • 0.3B • Updated • 154k • 98
My favorite Spaces.